Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1024 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.3461. Min Range: -6.3461

Max Act: 6.3461. Min Act: -0.0000

Data Index: 188832 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 6.3461. Min Range: -6.3461

Max Act: 5.4342. Min Act: -0.0000

Data Index: 752568 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 6.3461. Min Range: -6.3461

Max Act: 5.0729. Min Act: -0.0000

Data Index: 1241062 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 6.3461. Min Range: -6.3461

Max Act: 4.9288. Min Act: -0.0000

Data Index: 365341 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 6.3461. Min Range: -6.3461

Max Act: 4.5847. Min Act: -0.0000

Data Index: 1347909 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 6.3461. Min Range: -6.3461

Max Act: 4.3144. Min Act: -0.0000

Data Index: 4253 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 6.3461. Min Range: -6.3461

Max Act: 4.1929. Min Act: -0.0000

Data Index: 277208 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 6.3461. Min Range: -6.3461

Max Act: 3.8308. Min Act: -0.0000

Data Index: 178225 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 6.3461. Min Range: -6.3461

Max Act: 3.5101. Min Act: -0.0000

Data Index: 568171 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 6.3461. Min Range: -6.3461

Max Act: 3.3384. Min Act: -0.0000

Data Index: 1207427 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 6.3461. Min Range: -6.3461

Max Act: 3.6304. Min Act: -0.0000

Data Index: 1215613 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 6.3461. Min Range: -6.3461

Max Act: 3.7519. Min Act: -0.0000

Data Index: 1155914 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 6.3461. Min Range: -6.3461

Max Act: 3.4308. Min Act: -0.0000

Data Index: 668199 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 6.3461. Min Range: -6.3461

Max Act: 3.3893. Min Act: -0.0000

Data Index: 1095987 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 6.3461. Min Range: -6.3461

Max Act: 3.3691. Min Act: -0.0000

Data Index: 1342353 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 6.3461. Min Range: -6.3461

Max Act: 3.1852. Min Act: -0.0000

Data Index: 593146 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 6.3461. Min Range: -6.3461

Max Act: 3.3082. Min Act: -0.0000

Data Index: 75367 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 6.3461. Min Range: -6.3461

Max Act: 3.2989. Min Act: -0.0000

Data Index: 464725 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 6.3461. Min Range: -6.3461

Max Act: 3.4664. Min Act: -0.0000

Data Index: 428840 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 6.3461. Min Range: -6.3461

Max Act: 3.2956. Min Act: -0.0000

Data Index: 964252 (C4 (Web Text))

Max Activating Token Index: 107